© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2085
    Prev
    Next
    INDEX
    Explanations

    this is or encompasses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lends
    0.79
    뿜
    0.76
     acabou
    0.76
    자동
    0.75
     इसने
    0.71
    提供了
    0.71
     containing
    0.69
    ोने
    0.69
    迠
    0.68
     Celebrity
    0.68
    POSITIVE LOGITS
     vary
    1.31
     range
    1.26
     varies
    1.23
     manifest
    1.21
     ranges
    1.20
     refer
    1.20
     ranged
    1.17
    可以是
    1.16
    range
    1.16
    refer
    1.12
    Activations Density 0.428%

    No Known Activations